[Mesa-dev] [PATCH] i965/blorp: Use LRP instruction to do manual blending.

[Matt Turner]

Replaces (samples - 1) ADDs and a MUL with (samples - 1) LRPs.
---
 src/mesa/drivers/dri/i965/brw_blorp_blit.cpp |   31 +++++++++++--------------
 1 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_blorp_blit.cpp b/src/mesa/drivers/dri/i965/brw_blorp_blit.cpp
index 37524ad..4d1ba90 100644
--- a/src/mesa/drivers/dri/i965/brw_blorp_blit.cpp
+++ b/src/mesa/drivers/dri/i965/brw_blorp_blit.cpp
@@ -1376,12 +1376,11 @@ brw_blorp_blit_program::manual_blend(unsigned num_samples)
     * For integer formats, we replace the add operations with average
     * operations and skip the final division.
     */
-   typedef struct brw_instruction *(*brw_op2_ptr)(struct brw_compile *,
-                                                  struct brw_reg,
-                                                  struct brw_reg,
-                                                  struct brw_reg);
-   brw_op2_ptr combine_op =
-      key->texture_data_type == BRW_REGISTER_TYPE_F ? brw_ADD : brw_AVG;
+   struct brw_reg zero_point_five;
+   if (key->texture_data_type == BRW_REGISTER_TYPE_F) {
+      brw_MOV(&func, zero_point_five, brw_imm_f(0.5f));
+   }
+
    unsigned stack_depth = 0;
    for (unsigned i = 0; i < num_samples; ++i) {
       assert(stack_depth == _mesa_bitcount(i)); /* Loop invariant */
@@ -1423,9 +1422,17 @@ brw_blorp_blit_program::manual_blend(unsigned num_samples)
 
          /* TODO: should use a smaller loop bound for non_RGBA formats */
          for (int k = 0; k < 4; ++k) {
-            combine_op(&func, offset(texture_data[stack_depth - 1], 2*k),
+            if (key->texture_data_type == BRW_REGISTER_TYPE_F) {
+               /* LRP operands are (a, y, x). */
+               brw_LRP(&func, offset(texture_data[stack_depth - 1], 2*k),
+                       zero_point_five,
+                       offset(vec8(texture_data[stack_depth]), 2*k),
+                       offset(vec8(texture_data[stack_depth - 1]), 2*k));
+            } else {
+               brw_AVG(&func, offset(texture_data[stack_depth - 1], 2*k),
                        offset(vec8(texture_data[stack_depth - 1]), 2*k),
                        offset(vec8(texture_data[stack_depth]), 2*k));
+            }
          }
       }
    }
@@ -1433,16 +1440,6 @@ brw_blorp_blit_program::manual_blend(unsigned num_samples)
    /* We should have just 1 sample on the stack now. */
    assert(stack_depth == 1);
 
-   if (key->texture_data_type == BRW_REGISTER_TYPE_F) {
-      /* Scale the result down by a factor of num_samples */
-      /* TODO: should use a smaller loop bound for non-RGBA formats */
-      for (int j = 0; j < 4; ++j) {
-         brw_MUL(&func, offset(texture_data[0], 2*j),
-                 offset(vec8(texture_data[0]), 2*j),
-                 brw_imm_f(1.0/num_samples));
-      }
-   }
-
    if (key->tex_layout == INTEL_MSAA_LAYOUT_CMS)
       brw_ENDIF(&func);
 }
-- 
1.7.8.6